Plenoptic sampling

Chai, Jinxiang; Tong, Xin; Chan, S.C.; Shum, Heung-Yeung

doi:10.1145/344779.344932

Cited by 604 publications

(561 citation statements)

References 23 publications

Supporting

Mentioning

554

Contrasting

Order By: Relevance

“…To extend our method to cover much larger depth variation, we give the optimal depth segmentation using much fewer number of images, without loss of rendering quality. It is worth to mention that we get similar but more general results compared to the geometric analysis of [6], and the spectral analysis of [7], in particular, when the rendering camera is not on the capturing camera plane. In the current optical analysis, the occlusion problem is not discussed.…”

Section: Discussionsupporting

confidence: 64%

See 1 more Smart Citation

Optical Analysis of Light Field Rendering

Feng¹,

Shum

Image-Based Rendering

View full text Add to dashboard Cite

show abstract

Section: Discussionsupporting

confidence: 64%

“…Chai et al. [7] analyze the relationship among scene complexity, number of image samples, and output resolution. Furthermore, based on a spectral analysis of sampled light field.…”

Section: Introductionmentioning

confidence: 99%

Optical Analysis of Light Field Rendering

Feng¹,

Shum

Image-Based Rendering

View full text Add to dashboard Cite

show abstract

“…Light field rendering can be directly extended to incorporate discrete [8,9] or even continuous time steps [10]. To cover a larger degree of viewing angles at acceptable image quality, however, a large number of densely packed images are necessary [11][12][13]. By employing a prefiltering step the number of necessary samples can be reduced, but at the cost of more blurry output images [14][15][16].…”

Section: Related Workmentioning

confidence: 99%

Towards Plenoptic Raumzeit Reconstruction

Eisemann

Klose

Magnor

2011

Video Processing and Computational Video

View full text Add to dashboard Cite

Abstract. The goal of image-based rendering is to evoke a visceral sense of presense in a scene using only photographs or videos. A huge variety of different approaches have been developed during the last decade. Examining the underlying models we find three different main categories: view interpolation based on geometry proxies, pure image interpolation techniques and complete scene flow reconstruction. In this paper we present three approaches for free-viewpoint video, one for each of these categories and discuss their individual benefits and drawbacks. We hope that studying the different approaches will help others in making important design decisions when planning a free-viewpoint video system.

show abstract

“…The parameters of these primitives can be modeled with simple distributions such as uniform or gaussian. The priors are similar to imposters [8,4] commonly used in graphics, but differ in that no fixed primitive is specified. Furthermore as will be shown in Section 5, the prior need not be a parameterized shape.…”

Section: Reducing Distortions In Viewsmentioning

confidence: 99%